Monte Carlo Lab — R&D Boundary
How MARS uses this
The R&D boundary exists because simulated territory includes places the live account must never casually visit. The depth-duration map makes the boundary concrete: experiments may explore the deep-slow tail freely, but nothing graduates to live authority while its distribution still lives there.
How it benefits you
Drawdown stops being one scary number. A 7% dip reads as the common, quick-recovery event the map says it is, while the non-linear duration curve makes the case for gate compression viscerally: deep holes do not just cost more - they cost longer.
The deep-slow tail is legal territory for research and forbidden territory for live rules — the boundary in one picture.
The boundary
Simulation outputs flow into understanding — expected ranges, stress envelopes, scenario verdicts. They never flow directly into sizing. No simulated result, however flattering, can raise a gate cap, unlock a tier, or justify an override. Live authority belongs to live evidence and the gate ladder.
What gets sandboxed
Branch-weight profiles, rule changes, and sensitivity experiments run here first — against the Standard baseline over a persistence window, with documented verdicts — before deliberate promotion. 'I tried it and it felt better' is exactly the process MARS exists to replace.
Why the wall matters
Overfitting scenarios to recent regimes produces beautiful but fragile projections. The boundary means a fragile projection can waste research time but can never waste capital — the worst case of bad simulation is a bad memo, not a bad drawdown.
Graduation criteria
04A candidate finding leaves the sandbox only after it repeats across resampling seeds, survives adjacent parameter values, and holds up in the most recent evidence window. One flattering distribution is curiosity; the same shape across perturbations is structure. The boundary's paperwork exists to tell those two apart.
Further illustration
Four scenario profiles judged side by side: expectancy, adverse-tail cost, and a verdict. Changes graduate through this grid or not at all.
BASELINE
LIVEcurrent governing profile
TIGHTER STOPS
REJECTEDEV cost exceeds drawdown saving
TNP WEIGHT +10
SANDBOXedge up, adverse tail deepens
FEE MODEL B
CANDIDATEfriction saving survives resampling
Doctrine
Connected inside MARS
Go deeper
Deep dive — 01
The engine cannot write to the source workbook. The wall is a file permission, not a promise.
Read the full brief →
Deep dive — 02
Same seed, different structure: the only honest way to ask whether a change did anything.
Read the full brief →
Deep dive — 03
Path count buys precision, not truth. When the margin is thin, the error band decides.
Read the full brief →
Take it further
The research boundary exists because production rules must not move on a hunch. The Foundry is where a hunch can be taken seriously without ever touching a live rule.
Open the AlphaRail Foundry Lab ↗One price. Eleven workbooks, three TradingView indicators, and the full manual library — $497.
